{ "openapi": "3.0.1", "info": { "title": "๐ŸŽฌ YouTube Transcript Scraper", "description": "Turn any YouTube video, playlist or channel into clean, structured text. Bulk-extract transcripts and captions in 75 languages, plus views, likes, comments, keywords and thumbnails. Text array, plain text, WebVTT or SRT โ€” ready for AI training data, RAG pipelines, summarisation and SEO.", "version": "1.0", "x-build-id": "tRG9qlV1QvTDKQ3PB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/citrine_venus~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-citrine_venus-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/citrine_venus~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-citrine_venus-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/citrine_venus~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-citrine_venus-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "urls": { "title": "๐Ÿ”— YouTube URLs", "type": "array", "description": "๐Ÿ“ **Required (unless you use search keywords).** Paste one or more YouTube links.\n\nโœ… Supported:\nโ€ข Video โ€” `https://www.youtube.com/watch?v=VIDEO_ID`\nโ€ข Short โ€” `https://www.youtube.com/shorts/VIDEO_ID`\nโ€ข Short link โ€” `https://youtu.be/VIDEO_ID`\nโ€ข Playlist โ€” `https://www.youtube.com/playlist?list=PLAYLIST_ID`\nโ€ข Channel โ€” `https://www.youtube.com/@handle`\n\n๐Ÿ“บ Playlists and channels are expanded into individual videos, up to **Max videos per source** below.", "items": { "type": "string" } }, "searchKeywords": { "title": "๐Ÿ” Search keywords (optional)", "type": "array", "description": "๐Ÿ’ก No links handy? Type what you're looking for and we'll grab the transcripts of the top matching videos โ€” e.g. `lofi hip hop`, `apify tutorial`, `python asyncio`. Results are added on top of any URLs above.", "items": { "type": "string" } }, "scrapeShorts": { "title": "๐Ÿ“ฑ Include YouTube Shorts", "type": "boolean", "description": "๐Ÿฉณ When **ON**, Shorts (videos of 60 seconds or less) found inside channels, playlists and searches are included too. When **OFF** they are skipped. A Shorts link you paste yourself is always processed.", "default": false }, "maxVideosPerSource": { "title": "๐Ÿ“ฌ Max videos per playlist / channel / keyword", "minimum": 1, "maximum": 1000, "type": "integer", "description": "๐ŸŽš๏ธ How many videos to take from **each** playlist, channel or search keyword. Individual video links are never limited by this. Keep it low for a quick, cheap test run.", "default": 10 }, "maxResults": { "title": "๐Ÿ›‘ Overall video limit (0 = no limit)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "๐Ÿงฎ A hard ceiling on how many videos the whole run will process, after everything has been expanded and de-duplicated. Leave at `0` to process every video found.", "default": 0 }, "outputFormat": { "title": "๐Ÿงพ Transcript format", "enum": [ "json", "text", "vtt", "srt" ], "type": "string", "description": "๐Ÿ“„ Pick how the transcript is delivered in the `captions` field:\n\nโ€ข **Text array** โ€” one clean line per caption (best for AI, search and analytics) ๐Ÿงฉ\nโ€ข **Single line text** โ€” the entire transcript as one continuous string ๐Ÿ“„\nโ€ข **WebVTT** โ€” ready-to-use `.vtt` subtitles with timings ๐ŸŽž๏ธ\nโ€ข **SubRip (SRT)** โ€” ready-to-use `.srt` subtitles with timings ๐ŸŽฌ", "default": "json" }, "language": { "title": "๐ŸŒ Preferred caption language", "enum": [ "en", "es", "pt", "fr", "de", "it", "nl", "pl", "ru", "uk", "tr", "ar", "he", "fa", "hi", "bn", "ta", "te", "mr", "ur", "gu", "kn", "ml", "pa", "id", "ms", "th", "vi", "ja", "ko", "zh-Hans", "zh-Hant", "sv", "da", "no", "fi", "cs", "sk", "hu", "ro", "bg", "el", "hr", "sr", "sl", "lt", "lv", "et", "ca", "gl", "eu", "af", "sw", "am", "ha", "yo", "zu", "fil", "my", "km", "lo", "ne", "si", "az", "kk", "uz", "ka", "hy", "sq", "mk", "bs", "is", "ga", "cy", "mt", "la" ], "type": "string", "description": "๐Ÿ—ฃ๏ธ Which caption track to prefer. If the video has no track in this language we automatically fall back to English, then to whatever the video does offer โ€” so you still get a transcript.", "default": "en" }, "channelNameBoolean": { "title": "๐Ÿ“บ Channel Name", "type": "boolean", "description": "Add the channel name the video was published on โ€” e.g. `Selena Gomez`.", "default": false }, "channelIDBoolean": { "title": "๐Ÿ†” Channel ID", "type": "boolean", "description": "Add the channel's unique ID โ€” e.g. `UCjK8ORC71kwyj1DWFwril_A`.", "default": false }, "datePublishedBoolean": { "title": "๐Ÿ“… Date Published", "type": "boolean", "description": "Add the full publish timestamp โ€” e.g. `2024-02-22T23:00:12.000Z`.", "default": false }, "dateTextBoolean": { "title": "๐Ÿ—“๏ธ Date Text", "type": "boolean", "description": "Add the friendly publish date โ€” e.g. `Feb 22, 2024`.", "default": false }, "relativeDateTextBoolean": { "title": "โณ Relative Date Text", "type": "boolean", "description": "Add how long ago the video went live โ€” e.g. `2 years ago`.", "default": false }, "viewCountBoolean": { "title": "๐Ÿ‘€ View Count", "type": "boolean", "description": "Add the view count โ€” e.g. `27,406,159 views`.", "default": false }, "likesBoolean": { "title": "๐Ÿ‘ Likes", "type": "boolean", "description": "Add the number of likes โ€” e.g. `564,840`.", "default": false }, "commentsBoolean": { "title": "๐Ÿ’ฌ Comments", "type": "boolean", "description": "Add the number of comments โ€” e.g. `30,915`.", "default": false }, "keywordsBoolean": { "title": "๐Ÿท๏ธ Keywords", "type": "boolean", "description": "Add the video's tags / keywords as a comma-separated string.", "default": false }, "thumbnailBoolean": { "title": "๐Ÿ–ผ๏ธ Thumbnail URL", "type": "boolean", "description": "Add a direct link to the video's thumbnail image.", "default": false }, "descriptionBoolean": { "title": "๐Ÿ“„ Description", "type": "boolean", "description": "Add the full video description text.", "default": false }, "maxConcurrency": { "title": "โšก Parallel videos", "minimum": 1, "maximum": 16, "type": "integer", "description": "๐Ÿš€ How many videos to work on at the same time. Higher is faster but pushes harder on the target. `4` is a good balance for most runs.", "default": 4 }, "requestDelaySecs": { "title": "๐Ÿข Delay between requests (seconds)", "minimum": 0, "maximum": 10, "type": "number", "description": "โฑ๏ธ A polite pause before each request starts. Decimals allowed. Raise it if you are scraping a very large batch; `0` removes the pause entirely.", "default": 1 }, "maxRetries": { "title": "๐Ÿ” Maximum retries", "minimum": 3, "maximum": 12, "type": "integer", "description": "๐Ÿ›Ÿ How many times a single video is retried before it is skipped. Raise this if you are collecting a big batch and want the best possible success rate.", "default": 8 }, "proxyConfiguration": { "title": "๐Ÿ›ก๏ธ Network configuration", "type": "object", "description": "๐ŸŒ **Optional โ€” leave off unless you need it.** Blocking is handled for you automatically. Only change this if your workflow requires a specific network route or country.", "default": { "useApifyProxy": false } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }